All authors
Claude Skills by Mozurok
github.com/Mozurok121 skills1 installs108 views
- Invariants And Non GoalsIdentify the invariants, non-goals, and forbidden changes for the active task, then persist them as INVARIANTS_AND_NON_GOALS.md so implementation boundaries are locked before planning or coding. Use when impact analysis is done or mostly clear, the task may touch sensitive behavior or contracts or schema or runtime paths, and implementation boundaries need to be locked before planning or coding. Do not use when the task is still too unclear to define safe boundaries, the current need is to as...Votes: 0GitHub stars: 7
- Inventory SnapshotSnapshot the upstream Figma component library into docs/research/_inventory/figma_components.md. For each Figma component: name, inferred tier, node ID, and whether a spec/code/story exists in the WOS-UI surface. Produces delta vs previous snapshot. Use after design ships a Figma library update or to seed the inventory at project start. Do not use when no Figma source is available or when only auditing one component (use design-spec-review instead).Votes: 0GitHub stars: 7
- Journey MapDocument a user journey from screen references and a user story input. Produces a journey spec doc matching the JOURNEY_SPEC.md template with outcome, screen flow, components consumed, critical states, accessibility, security, and performance sections. Use when mapping a user flow across multiple screens. Do not use when documenting a single screen (use screen-spec) or a reusable pattern (use pattern-doc).Votes: 0GitHub stars: 7
- Jtbd Switch InterviewerSenior product researcher running Jobs-to-be-Done switch interviews to surface the four forces of adoption (push, pull, anxiety, habit) and the trigger, struggle and switch timeline. Replaces internal motivation assumptions with verbatim user evidence. Activates when the charter or the source of truth mentions user research or PMF with no captured methodology, or when a draft decision rests on motivation assumptions with no interview behind it. Do not use for solo ideation with no reachable u...Votes: 0GitHub stars: 7
- Mcp Server VetRead-only safety inspection of a third-party MCP server BEFORE it is added to a config or trusted. Reads the declared tool descriptions, input schemas, scopes, transport, and env and secret surface, which the README alone does not carry, compares declared behavior against what the tools expose, scans for tool-description poisoning, over-broad scopes, egress and credential access, config tampering and hidden Unicode, and returns an add, decline or sandbox verdict for a human to approve. Never ...Votes: 0GitHub stars: 7
- Migration Safety StewardSenior database migration safety steward auditing DDL for production-unsafe patterns BEFORE the migration is applied. Catches NOT NULL without backfill, a column drop without two-phase deploy, a rename without a double-write window, CREATE INDEX without CONCURRENTLY, ALTER TYPE rewriting a whole table, an FK add without the NOT VALID and VALIDATE split, and irreversible type narrowing. Activates when a plan slice includes schema changes, when the files in scope include migrations, or when a s...Votes: 0GitHub stars: 7
- Pattern DocDocument a reusable UX pattern (empty state, error handling, confirmation dialog, search-filter-sort, loading skeleton) that applies across multiple screens and projects. Produces a pattern spec doc matching the PATTERN_SPEC.md template. Use when formalizing a recurring UX solution. Do not use when documenting a single component (use component-spec) or a project-specific journey (use journey-map).Votes: 0GitHub stars: 7
- Performance BudgetSenior performance-budget auditor that declares the numeric non-functional budgets a change must hold (Core Web Vitals, backend latency percentiles, payload and bundle size, key-operation cost) and the action when a metric regresses. Produces PERFORMANCE_BUDGET.md, a per-metric table of threshold, statistic, measurement source and regression action. Spec-only; it never runs load tests itself. Also covers React Native plus Godot 2D-mobile and 3D surfaces (frame budget, draw calls). Activates w...Votes: 0GitHub stars: 7
- Portfolio ReviewRead-only cross-task board across every active task in all projects. Runs scripts/portfolio-review.sh to classify each active task as done-unclosed, blocked, my-move, stale, or in-flight, then renders one ranked board with a single recommended next action per row, so picking the next thread and catching finished-but-unarchived tasks stop depending on memory. An --outcomes mode reports closed-task outcome telemetry (merge status, cycle time) instead of the live board. Use when you have many co...Votes: 0GitHub stars: 7
- Post Deploy VerifierSenior reliability engineer producing a per-slice post-deploy verification plan that maps each acceptance criterion to a concrete live signal (log query, dashboard panel, smoke test, flag check, DB invariant query), plus negative checks and a rollback trigger checklist. Activates after a deploy with no paired plan, when branch-commit produced a deploy without post-deploy checks, or when slice-closure is about to close a slice without one. Do not use BEFORE the slice ships (use verify-against-...Votes: 0GitHub stars: 7
- Post Review PivotCapture what a PR or team review changed about the intended behavior or approach, separate keep from revert or replace, and produce the smallest safe set of updates to task memory and follow-on work. Does not implement product code. Use when review requests a meaningful direction change (wrong fields, wrong migrations, wrong integration shape), or when you need a structured pivot digest before rewriting the plan or slices. Do not use when feedback is primarily corrective under the existing co...Votes: 0GitHub stars: 7
- Postmortem AuthorSenior reliability engineer authoring a blameless postmortem for a resolved incident: a timeline, contributing causes rather than blame, impact measured against the SLO and error budget, and concrete action items with owners. Produces POSTMORTEM.md. Activates when incident-triage resolved an escalation or a significant hotfix with an identified root cause, when task-close ends an incident-driven task, or when a notable outage needs a standalone learning record. Do not use for live triage (use...Votes: 0GitHub stars: 7
- Pr Feedback IngestTurn PR feedback (Greptile, CI, bots, humans) into a structured traceable backlog aligned with the task artifacts, so the next execution step can be a narrow implement-approved-slice or a small planning touch without losing alignment. Corrective scope only. Use when a PR is open with review feedback and you want each item mapped to files, slices, and memory updates before coding. Do not use when feedback requires a new product direction or contract (use post-review-pivot), when there is no fe...Votes: 0GitHub stars: 7
- Pr PackagePrepare a clean delivery package for GitHub from the real git diff against an explicit base branch, persisted as PR_PACKAGE.md. Produces the branch name, commit messages, the git commands, PR title and body, and reviewer attention points, and never invents work outside the diff. Per-repo when SOURCE_OF_TRUTH.md has a Repositories section. Use when scope is complete and the diff is real and stable. Do not use during active implementation, when the diff is still changing, when you only need a q...Votes: 0GitHub stars: 7
- Problem FramingRun a short socratic intake that questions whether the stated problem is the right problem BEFORE a task exists, then write a task-level BRIEF.md (problem statement, success criteria, non-goals, recommended approach, named deliverables) that task-init consumes. Asks one question at a time and prefers multiple choice. Use when an objective is fuzzy, broad, or possibly mis-scoped and worth shaping before any task folder is created. Do not use when the objective is already specific enough to sta...Votes: 0GitHub stars: 7
- Project BootstrapInitialize a new project context inside the task repository before any task exists. Creates projects/<client>__<project>/, PROJECT_CHARTER.md, REFERENCES.md skeleton, and active/ plus archive/ subfolders so subsequent task-init runs have grounded project-level memory to consume. Use when starting a brand-new project, product, initiative, or client engagement, projects/<client>__<project>/ does not yet exist, or you need to capture project-level context (objective, stack, planned repositories,...Votes: 0GitHub stars: 7
- Prompt ShapeShape the best possible prompt for the current task and workflow phase. Aligns the prompt content with the intended editor mode and the chosen command's required inputs, producing a copy-paste-ready handoff. Use when prompt precision would materially improve the next workflow action, the next step is known but the current prompt or context is too vague or broad or missing required inputs for the chosen command, or the user wants a copy-paste-ready prompt aligned with the intended editor mode....Votes: 0GitHub stars: 7
- Release PlanDesign a pre-deploy release and rollout strategy: pick the rollout pattern (feature flag, canary, blue-green, or full progressive delivery) by risk and infra, then specify the exposure ramp, the promotion metric and threshold that advances each step, and the rollback trigger and mechanism. Produces RELEASE_PLAN.md. Stack- and infra-agnostic; it designs the rollout, it does not execute it. Gated --godot-mobile and --godot-desktop modes plan a store or desktop ship, both off by default. Use whe...Votes: 0GitHub stars: 7
- Repo Consistency SweepProactive defect-class detection that handles the lower-value half of code review, so human reviewers stay on design, intent, and knowledge transfer. Catches convention drift, ordering bugs, type-safety gaps, security and multi-tenant invariants (CWE-grounded), and operability issues against a curated bug-class library before PR packaging. Runs after review-hard, before pr-package, and suppresses findings the user declined until the file changes. The library grows through pr-feedback-ingest, ...Votes: 0GitHub stars: 7
- Resolve Contract GapsTurn unresolved or contradictory behavior, contract, or policy gaps into one canonical implementation-safe decision set, then persist the result in DECISIONS.md and TASK_STATE.md as explicit reviewable proposals (not silent intent changes). Use when key ambiguities have already been identified, the task has enough facts to compare options safely, contradictory rules or assumptions or interpretations still exist, and planning cannot proceed safely until one canonical rule set is established. D...Votes: 0GitHub stars: 7
- Resume From StateResume the task from TASK_STATE.md and the linked artifacts, reconstruct the current truth, and determine the best next step. Brings back full context after a session break or a chat switch. Also owns the explicit --lost-session recovery mode for when the transcript itself is lost: a capped, read-only sweep of the harness session files that proposes context with provenance. Use when work resumes in a new chat, or the task was paused and needs fast reconstruction. Do not use for a brand-new ta...Votes: 0GitHub stars: 7
- Review HardReview the current task changes for real correctness, safety, and maintainability risks before slice closure or PR prep, and recommend the smallest safe next step. Surfaces meaningful issues (not cosmetic feedback); not a replacement for external review systems. Returns no-op when the review would not materially change conclusions. Use when a slice or task-level implementation was completed, the user wants a focused engineering risk review before closure or PR prep, or the current need is to ...Votes: 0GitHub stars: 7
- Rls Auth Boundary AuditorSenior Supabase RLS and auth boundary auditor for tenant isolation gaps in migrations and policy DDL BEFORE deploy. Checks effective write predicates, including implicit USING fallback when WITH CHECK is omitted, RLS enabled without FORCE ROW LEVEL SECURITY, missing policies on join and audit tables, missing tenant predicates, SECURITY DEFINER functions without RLS-aware guards, and unjustified service_role bypass. Activates when a Supabase or multi-tenant decision lands with no RLS policy lo...Votes: 0GitHub stars: 7
- Screen Spec FleetGenerate one spec document per screen in parallel from Figma frames, dispatching one worker per screen and merging SCREEN_MAP.md and routes.md from their partials. The orchestrator-workers variant of screen-spec. Use when the screen count is 6 or more, a Figma MCP is reachable, and foundations plus SCREEN_MAP already exist. Do not use for a single screen (use screen-spec), when foundations are missing (use design-bootstrap first), or when the frames have not been enumerated yet, since the cal...Votes: 0GitHub stars: 7
- Screen SpecGenerate a screen specification from a Figma frame using MCP tools (get_design_context, get_screenshot). Produces a spec doc matching the SCREEN_SPEC.md template with layout sketch, components used, spacing observed, data dependencies, copy, accessibility notes, interactions, and error states. Use when documenting a specific screen. Do not use when the screen has no Figma frame or when the spec already exists. For 6 or more screens, use screen-spec-fleet. Once screens document raw values, use...Votes: 0GitHub stars: 7
- Security ReviewDedicated security review of the current task changes covering threat modeling, OWASP ASVS L1 checklist pass, auth/authz flow tracing, and dependency/secret scanning reminders. Distinct from review-hard (general risk) and repo-consistency-sweep (pattern matching). Activates when DECISIONS.md, IMPLEMENTATION_PLAN.md, or TASK_STATE.md's Active files in scope names an auth or biometric-scoped change without a completed security-review for that scope. Use when the task touches authentication, aut...Votes: 0GitHub stars: 7
- Self Critique And ReviseTake a draft artifact (IMPLEMENTATION_PLAN.md, SLICES/*.md, or PR_PACKAGE.md), run a structured critique against a locked per-artifact-type rubric, and produce a revised draft. Evaluator-optimizer pattern; the revision is written APPLIED in every mode, the critique is shown in the response, and git is the undo. Distinct from review-hard (judges, no revision), direction-adjust (records a decision, no revision), and post-review-pivot (external feedback). Use when a draft was just written and on...Votes: 0GitHub stars: 7
- Skill VetRead-only safety inspection of a third-party agent skill or plugin BEFORE it is installed or trusted. Reads every file in the candidate directory (SKILL.md plus auxiliary and test files, not just the body), compares declared behavior against what the files actually do, scans for exfiltration, secret access, config or agent-instruction modification, shell execution, and hidden Unicode, and returns an install/decline/sandbox verdict for a human to approve. Never installs, never auto-trusts. Use...Votes: 0GitHub stars: 7
- Slice ClosureDecide whether the current slice is ready to close, distinguishing slice completion from full task completion, then persist the result in slice notes and TASK_STATE.md as explicit reviewable closure notes. For single-slice tasks may route directly to delivery. Returns no-op when slice memory would not materially change. Use when a slice was just implemented, slice-level validation was completed or reviewed, or the next decision is whether this slice can be closed cleanly. Do not use when no c...Votes: 0GitHub stars: 7
- Slo DefineSenior reliability engineer defining a service's reliability contract: choose SLIs, set an SLO target and measurement window, compute the error budget, and write the error-budget policy for when that budget is exhausted. Produces SLO_SPEC.md. Spec-only; it defines the contract, it does not instrument it. Activates when a service or a critical user flow has no documented SLO, or when a reliability target is named with no SLIs or error budget behind it. Do not use when there is no observability...Votes: 0GitHub stars: 7
- Stack Currency CheckVerify that the patterns the model is about to use for a given framework+version are current per official docs, and cache the result as CURRENT_PATTERNS.md at the project level. Prevents the "gold-standard audit" anti-pattern where training-data defaults ship outdated patterns (e.g. Supabase getSession when getUser is current, sequential await when Promise.all is recommended). Use when impact-analysis flags greenfield work in an established framework, when starting a new project with framewor...Votes: 0GitHub stars: 7
- Stack RecommendResearch and recommend a technology stack for the active project by consulting official documentation, quality articles, and AAA company practices for latest stable versions. Accepts optional user-provided reference links. Produces a STACK_RECOMMENDATION.md inside the active task folder with versioned recommendations, compatibility notes, and trade-offs grounded in sources. Use when the project stack is undecided or needs validation, when starting a new project from zero, or when evaluating a...Votes: 0GitHub stars: 7
- State ReconcileDetect drift between TASK_STATE.md, other task-memory artifacts, and observable reality (code, tests, diff when provided), then propose the minimum set of updates so operational memory is trustworthy again. Use when TASK_STATE.md is stale or internally inconsistent after many edits, IMPLEMENTATION_PLAN.md or SLICES/*.md or slice status disagree with each other or with what was actually done, you need a full cross-check before trusting routing or before delivery prep, or the user explicitly wa...Votes: 0GitHub stars: 7
- Sync Task StateUpdate TASK_STATE.md so it reflects the latest operational truth of the task and can be resumed safely in this or another session. Lighter-weight than state-reconcile (no cross-artifact drift detection); preferred when the update is incremental and trusted. Use when a meaningful planning, decision, implementation, or closure step just happened, a slice was completed or closed, canonical decisions changed, the task is about to be paused or handed off, or TASK_STATE.md is stale relative to curr...Votes: 0GitHub stars: 7
- Targeted QuestionsAsk the minimum set of high-value factual questions needed to proceed safely, then persist the result in the task repository. Distinct from decision-interview (factual gaps, not decision-driven gaps). Use when impact analysis or boundary definition revealed missing facts, correctness depends on information that is not yet confirmed, or the task cannot safely move into planning or implementation without clarification. Do not use when the main problem is missing policy or behavioral decisions r...Votes: 0GitHub stars: 7
- Task ClosePerform the terminal task lifecycle transition for a finished task: verify the spec done-conditions, set TASK_STATE.md to its final closed state, and move the task folder from active/ to archive/. The symmetric counterpart to task-init and the only official way to close a whole task. Use when every slice is closed, the work is merged or explicitly waived, and the whole task is ending. Do not use when only a single slice is ending (use slice-closure), when implementation or review is still in ...Votes: 0GitHub stars: 7
- Task Init FleetOrchestrator-workers variant of task-init for decomposing a complex brief into N parallel independent sub-tasks. Orchestrator validates the decomposition (no overlap, clear scope per sub-task, cross-links justified); N mechanical-role workers each run a full task-init in parallel producing one task folder with 5 mandatory files. Use when the user's brief contains N >= 3 logically independent work streams (e.g., REST->GraphQL migration across api-server + mobile-app + web-app; or implement-X f...Votes: 0GitHub stars: 7
- Task InitInitialize the official task folder and base task memory inside projects/<client>__<project>/active/YYYY-MM-DD_<task-slug>/. Creates README.md, TASK_STATE.md, SOURCE_OF_TRUTH.md, DECISIONS.md, IMPLEMENTATION_PLAN.md; seeds from PROJECT_CHARTER.md when present; emits a multi-repo ## Repositories section in SOURCE_OF_TRUTH.md when 2+ repos are provided. Can seed from a vetted issue-tracker MCP item, gated and off by default. Use at the START of any engineering work in this workflow's repositori...Votes: 0GitHub stars: 7
- Task WorkspaceProvision, report, or attach a dedicated git worktree and branch for the active task on a git-backed project, so multiple tasks run in parallel on one repository without colliding on a single working tree. Opt-in and git-gated: a non-git project or an un-opted task is a no-op. Records the worktree path and task branch in SOURCE_OF_TRUTH.md and runs standalone to retrofit a task already in progress. Use when a task needs an isolated working tree and branch, or to attach one to an in-flight tas...Votes: 0GitHub stars: 7
- Team UpdateWrite a simple, natural English status update for any team channel (Slack, Discord, Teams, email, GitHub PR comment, standup notes), short, grounded, and professional. Channel-portable. Use when the user wants to communicate progress quickly to teammates or reviewers, implementation or planning has reached a meaningful checkpoint, or a short asynchronous note is the right channel (not a full PR description, not a long doc). Do not use when there is no meaningful progress to report, the user n...Votes: 0GitHub stars: 7
- Test StrategyDefine the smallest set of meaningful tests that protects behavior and reduces regression risk for the active task, then persist as TEST_STRATEGY.md plus a TASK_STATE.md update. Avoids forcing the artifact when it adds no material signal. Detects a Godot or Unity target and routes to the matching headless runner, treating the runtime gate as complementary to the headless suite. Use when the change affects important behavior, contracts, data flow, or regression risk, or when scope reads as aut...Votes: 0GitHub stars: 7
- Unity Scene PlanPlan the Unity GameObject hierarchy and component architecture for a 3D feature before any C# is written: the scene and prefab structure, what each MonoBehaviour owns, the input model, and, for multiplayer, the networked-authority declarations. Produces UNITY_SCENE_PLAN.md. Capability-routed and MCP-agnostic. A 3D plan SHALL declare its render pipeline and a multiplayer plan SHALL declare its topology, or the plan is incomplete. Do not use to frame whether the game idea is right (use problem-...Votes: 0GitHub stars: 7
- Verify Against Rubric FleetOrchestrator-workers generalization of verify-against-rubric to N=many artifacts against ONE locked rubric. Dispatches N stateless judgment-role sub-agents in parallel; each receives ONE artifact + the SAME rubric with read-only input access and one assigned JSON return-file write (no TASK_STATE, no DECISIONS, no prior history); returns structured per-criterion verdict. Orchestrator merges into VERIFICATION_LOG.md with aggregate pass/fail counts + failure clustering (which criteria fail most ...Votes: 0GitHub stars: 7
- Verify Against RubricSpawn a stateless sub-agent (Claude Code `Agent` tool, Cursor agent mode, or equivalent) with ONLY the artifact path plus the locked rubric plus read-only tools. Sub-agent returns a structured verdict (satisfied, needs_revision, or failed) plus per-criterion feedback. Distinct from self-critique-and-revise (same-context; rewrites in place). Use after pr-package, contract-signoff, or implement-approved-slice on HIGH-complexity slices when independent verification matters more than throughput. ...Votes: 0GitHub stars: 7
- Web Runtime VerifyVerify a built web or static frontend at runtime: serve the build, assert page identity first, run the web battery (overflow 320 to 2560, keyboard and focus, console errors, Lighthouse and axe when available), and decide a PASS/FAIL/BLOCKED gate. The run's real output IS the evidence; a claimed-but-not-shown run is unverified. It verifies and routes fixes, it does not apply them. Do not use to plan a page (implementation-plan), to write or fix code (implement-approved-slice), for numeric perf...Votes: 0GitHub stars: 7
- What NextDetermine the current stage of the active task and recommend the single best immediate next command, editor mode, and work complexity. Routes based on TASK_STATE.md, DECISIONS.md, and IMPLEMENTATION_PLAN.md without reopening broad discovery. Use when the user wants a fast operational answer for what to do next, when the task already has enough state to avoid rediscovery, and when the next step is not obvious from current artifacts. Do not use when the task is brand new (use task-init), when r...Votes: 0GitHub stars: 7
- Where We AtMacro checkpoint that assesses the real current task state against the approved plan and task artifacts, then determines what is done, what is missing, and what remains to finish the proposed work. Broader than slice closure. Returns no-op when the checkpoint would not materially change operational truth. Use when the user wants a reliable checkpoint on task progress, the task has multiple phases or slices, or the current need is broader than closing a single slice. Do not use when the task i...Votes: 0GitHub stars: 7
- Workflow GuidePedagogical onboarding helper that explains which command and editor mode should be used now, why, and the next 2-3 steps in a practical way for users still learning the workflow phases. Heavier than what-next; the heavier sequence is justified only when the user wants to understand the workflow itself. Use when the user wants a more guided explanation of the current moment, the user wants to understand the workflow itself, a short recommended sequence for the next few steps would be useful, ...Votes: 0GitHub stars: 7
- A11y AuditSenior accessibility auditor mapping a UI surface (screen, flow, or component set) to WCAG 2.2 at a named conformance level. Produces ACCESSIBILITY_AUDIT.md, a per-criterion conformance ledger that splits machine-checkable rows from a manual-review queue, with severity and concrete remediation per finding. Activates when a screen-spec or an implemented surface has no conformance ledger, or when a delivery surface needs a conformance pass before sign-off. Do not use for a contrast-only request...Votes: 0GitHub stars: 7
- Color Contrast ArchitectSenior design-system contrast architect enforcing WCAG 2.2 AA and AAA per design context (normal text, large text, UI components, focus indicators). Audits every documented foreground and background pair across the supplied themes BEFORE the visual choices lock, producing a pairwise contrast matrix with token-level remediation. Activates when design-bootstrap proposes tokens without contrast pairs, or when a screen-spec or component-spec mentions an unvalidated pair. Do not use for a single p...Votes: 0GitHub stars: 7